{"id":"W4408177377","doi":"10.1016/j.sbi.2025.103027","title":"Language models for protein design","year":2025,"lang":"en","type":"review","venue":"Current Opinion in Structural Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Protein design; Computational biology; Computer science; Linguistics; Biology; Protein structure; Biochemistry; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002516149,0.0004336666,0.0008517458,0.000196495,0.00005710827,0.00002075856,0.000506621,0.0005939313,0.00001025709],"category_scores_gemma":[0.0003258818,0.0003359964,0.0003062964,0.0001566565,0.00008218018,0.000004230281,0.0002456525,0.0003737814,0.000004454383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004386203,"about_ca_system_score_gemma":0.0002982419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003884063,"about_ca_topic_score_gemma":9.40372e-7,"domain_scores_codex":[0.998107,0.0002980412,0.0006682959,0.0004889775,0.0000581988,0.0003795555],"domain_scores_gemma":[0.9990486,0.00008016739,0.0003401146,0.0004294752,0.00005213479,0.00004951442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002670476,0.000008410389,0.000003291228,0.02283171,0.00004693178,6.34772e-8,0.00003257694,0.00009938092,0.00003533485,0.002378129,0.001163381,0.9733741],"study_design_scores_gemma":[0.0003593715,0.0001760431,6.141356e-7,0.004595458,0.00003601304,0.000008794206,0.000007043569,0.001245137,0.00001864452,0.0009140366,0.9922235,0.0004153649],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000007575473,0.9720386,0.02257586,0.00001046461,0.00260959,0.002270844,0.0003660885,0.00002192442,0.00009905073],"genre_scores_gemma":[0.00002502596,0.9851339,0.006328532,0.000010198,0.0005908359,0.0006782938,0.007054956,0.00002932161,0.0001489682],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9910601,"threshold_uncertainty_score":0.9999092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06558631815449587,"score_gpt":0.4139570759980702,"score_spread":0.3483707578435743,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}